Merge branch 'fix-unconnected-udp'

Daniel Borkmann says:

====================
Please refer to the patch 1/6 as the main patch with the details
on the current sendmsg hook API limitations and proposal to fix
it in order to work with basic applications like DNS. Remaining
patches are the usual uapi and tooling updates as well as test
cases. Thanks a lot!

v2 -> v3:
  - Add attach types to test_section_names.c and libbpf (Andrey)
  - Added given Acks, rest as-is
v1 -> v2:
  - Split off uapi header sync and bpftool bits (Martin, Alexei)
  - Added missing bpftool doc and bash completion as well
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

9 files changed, 228 insertions, 22 deletions

diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index ac26876389c2..e744b3e4e56a 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -29,7 +29,7 @@ CGROUP COMMANDS
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
 |	*ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** |
 |		**bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** |
-|		**sendmsg4** | **sendmsg6** | **sysctl** }
+|		**sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** }
 |	*ATTACH_FLAGS* := { **multi** | **override** }
 
 DESCRIPTION
@@ -86,6 +86,10 @@ DESCRIPTION
 		  unconnected udp4 socket (since 4.18);
 		  **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an
 		  unconnected udp6 socket (since 4.18);
+		  **recvmsg4** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
+                  an unconnected udp4 socket (since 5.2);
+		  **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for
+                  an unconnected udp6 socket (since 5.2);
 		  **sysctl** sysctl access (since 5.2).
 
 	**bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index e8118544d118..018ecef8dc13 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -40,7 +40,7 @@ PROG COMMANDS
 |		**lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
 |		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
 |		**cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** |
-|		**cgroup/sysctl**
+|		**cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl**
 |	}
 |       *ATTACH_TYPE* := {
 |		**msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector**
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 50e402a5a9c8..4300adf6e5ab 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -371,6 +371,7 @@ _bpftool()
                                 lirc_mode2 cgroup/bind4 cgroup/bind6 \
                                 cgroup/connect4 cgroup/connect6 \
                                 cgroup/sendmsg4 cgroup/sendmsg6 \
+                                cgroup/recvmsg4 cgroup/recvmsg6 \
                                 cgroup/post_bind4 cgroup/post_bind6 \
                                 cgroup/sysctl" -- \
                                                    "$cur" ) )
@@ -666,7 +667,7 @@ _bpftool()
                 attach|detach)
                     local ATTACH_TYPES='ingress egress sock_create sock_ops \
                         device bind4 bind6 post_bind4 post_bind6 connect4 \
-                        connect6 sendmsg4 sendmsg6 sysctl'
+                        connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl'
                     local ATTACH_FLAGS='multi override'
                     local PROG_TYPE='id pinned tag'
                     case $prev in
@@ -676,7 +677,7 @@ _bpftool()
                             ;;
                         ingress|egress|sock_create|sock_ops|device|bind4|bind6|\
                         post_bind4|post_bind6|connect4|connect6|sendmsg4|\
-                        sendmsg6|sysctl)
+                        sendmsg6|recvmsg4|recvmsg6|sysctl)
                             COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
                                 "$cur" ) )
                             return 0
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 7e22f115c8c1..73ec8ea33fb4 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -25,7 +25,8 @@
 	"       ATTACH_TYPE := { ingress | egress | sock_create |\n"	       \
 	"                        sock_ops | device | bind4 | bind6 |\n"	       \
 	"                        post_bind4 | post_bind6 | connect4 |\n"       \
-	"                        connect6 | sendmsg4 | sendmsg6 | sysctl }"
+	"                        connect6 | sendmsg4 | sendmsg6 |\n"           \
+	"                        recvmsg4 | recvmsg6 | sysctl }"
 
 static const char * const attach_type_strings[] = {
 	[BPF_CGROUP_INET_INGRESS] = "ingress",
@@ -42,6 +43,8 @@ static const char * const attach_type_strings[] = {
 	[BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4",
 	[BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6",
 	[BPF_CGROUP_SYSCTL] = "sysctl",
+	[BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4",
+	[BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6",
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 26336bad0442..7a4e21a31523 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1063,7 +1063,8 @@ static int do_help(int argc, char **argv)
 		"                 sk_reuseport | flow_dissector | cgroup/sysctl |\n"
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
-		"                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
+		"                 cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n"
+		"                 cgroup/recvmsg6 }\n"
 		"       ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
 		"                        flow_dissector }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 63e0cf66f01a..e4114a7e4451 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -192,6 +192,8 @@ enum bpf_attach_type {
 	BPF_LIRC_MODE2,
 	BPF_FLOW_DISSECTOR,
 	BPF_CGROUP_SYSCTL,
+	BPF_CGROUP_UDP4_RECVMSG,
+	BPF_CGROUP_UDP6_RECVMSG,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5d046cc7b207..151f7ac1882e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3210,6 +3210,10 @@ static const struct {
 						BPF_CGROUP_UDP4_SENDMSG),
 	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 						BPF_CGROUP_UDP6_SENDMSG),
+	BPF_EAPROG_SEC("cgroup/recvmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_UDP4_RECVMSG),
+	BPF_EAPROG_SEC("cgroup/recvmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_UDP6_RECVMSG),
 	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
 						BPF_CGROUP_SYSCTL),
 };
diff --git a/tools/testing/selftests/bpf/test_section_names.c b/tools/testing/selftests/bpf/test_section_names.c
index bebd4fbca1f4..dee2f2eceb0f 100644
--- a/tools/testing/selftests/bpf/test_section_names.c
+++ b/tools/testing/selftests/bpf/test_section_names.c
@@ -120,6 +120,16 @@ static struct sec_name_test tests[] = {
 		{0, BPF_CGROUP_UDP6_SENDMSG},
 	},
 	{
+		"cgroup/recvmsg4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG},
+		{0, BPF_CGROUP_UDP4_RECVMSG},
+	},
+	{
+		"cgroup/recvmsg6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG},
+		{0, BPF_CGROUP_UDP6_RECVMSG},
+	},
+	{
 		"cgroup/sysctl",
 		{0, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL},
 		{0, BPF_CGROUP_SYSCTL},
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 3f110eaaf29c..4ecde2392327 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -76,6 +76,7 @@ struct sock_addr_test {
 	enum {
 		LOAD_REJECT,
 		ATTACH_REJECT,
+		ATTACH_OKAY,
 		SYSCALL_EPERM,
 		SYSCALL_ENOTSUPP,
 		SUCCESS,
@@ -88,9 +89,13 @@ static int connect4_prog_load(const struct sock_addr_test *test);
 static int connect6_prog_load(const struct sock_addr_test *test);
 static int sendmsg_allow_prog_load(const struct sock_addr_test *test);
 static int sendmsg_deny_prog_load(const struct sock_addr_test *test);
+static int recvmsg_allow_prog_load(const struct sock_addr_test *test);
+static int recvmsg_deny_prog_load(const struct sock_addr_test *test);
 static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test);
+static int recvmsg4_rw_asm_prog_load(const struct sock_addr_test *test);
 static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test);
 static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test);
+static int recvmsg6_rw_asm_prog_load(const struct sock_addr_test *test);
 static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test);
 static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test);
 static int sendmsg6_rw_wildcard_prog_load(const struct sock_addr_test *test);
@@ -507,6 +512,92 @@ static struct sock_addr_test tests[] = {
 		SRC6_REWRITE_IP,
 		SYSCALL_EPERM,
 	},
+
+	/* recvmsg */
+	{
+		"recvmsg4: return code ok",
+		recvmsg_allow_prog_load,
+		BPF_CGROUP_UDP4_RECVMSG,
+		BPF_CGROUP_UDP4_RECVMSG,
+		AF_INET,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_OKAY,
+	},
+	{
+		"recvmsg4: return code !ok",
+		recvmsg_deny_prog_load,
+		BPF_CGROUP_UDP4_RECVMSG,
+		BPF_CGROUP_UDP4_RECVMSG,
+		AF_INET,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		"recvmsg6: return code ok",
+		recvmsg_allow_prog_load,
+		BPF_CGROUP_UDP6_RECVMSG,
+		BPF_CGROUP_UDP6_RECVMSG,
+		AF_INET6,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_OKAY,
+	},
+	{
+		"recvmsg6: return code !ok",
+		recvmsg_deny_prog_load,
+		BPF_CGROUP_UDP6_RECVMSG,
+		BPF_CGROUP_UDP6_RECVMSG,
+		AF_INET6,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		"recvmsg4: rewrite IP & port (asm)",
+		recvmsg4_rw_asm_prog_load,
+		BPF_CGROUP_UDP4_RECVMSG,
+		BPF_CGROUP_UDP4_RECVMSG,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SUCCESS,
+	},
+	{
+		"recvmsg6: rewrite IP & port (asm)",
+		recvmsg6_rw_asm_prog_load,
+		BPF_CGROUP_UDP6_RECVMSG,
+		BPF_CGROUP_UDP6_RECVMSG,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SUCCESS,
+	},
 };
 
 static int mk_sockaddr(int domain, const char *ip, unsigned short port,
@@ -765,8 +856,8 @@ static int connect6_prog_load(const struct sock_addr_test *test)
 	return load_path(test, CONNECT6_PROG_PATH);
 }
 
-static int sendmsg_ret_only_prog_load(const struct sock_addr_test *test,
-				      int32_t rc)
+static int xmsg_ret_only_prog_load(const struct sock_addr_test *test,
+				   int32_t rc)
 {
 	struct bpf_insn insns[] = {
 		/* return rc */
@@ -778,12 +869,22 @@ static int sendmsg_ret_only_prog_load(const struct sock_addr_test *test,
 
 static int sendmsg_allow_prog_load(const struct sock_addr_test *test)
 {
-	return sendmsg_ret_only_prog_load(test, /*rc*/ 1);
+	return xmsg_ret_only_prog_load(test, /*rc*/ 1);
 }
 
 static int sendmsg_deny_prog_load(const struct sock_addr_test *test)
 {
-	return sendmsg_ret_only_prog_load(test, /*rc*/ 0);
+	return xmsg_ret_only_prog_load(test, /*rc*/ 0);
+}
+
+static int recvmsg_allow_prog_load(const struct sock_addr_test *test)
+{
+	return xmsg_ret_only_prog_load(test, /*rc*/ 1);
+}
+
+static int recvmsg_deny_prog_load(const struct sock_addr_test *test)
+{
+	return xmsg_ret_only_prog_load(test, /*rc*/ 0);
 }
 
 static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test)
@@ -838,6 +939,47 @@ static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test)
 	return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
 }
 
+static int recvmsg4_rw_asm_prog_load(const struct sock_addr_test *test)
+{
+	struct sockaddr_in src4_rw_addr;
+
+	if (mk_sockaddr(AF_INET, SERV4_IP, SERV4_PORT,
+			(struct sockaddr *)&src4_rw_addr,
+			sizeof(src4_rw_addr)) == -1)
+		return -1;
+
+	struct bpf_insn insns[] = {
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+		/* if (sk.family == AF_INET && */
+		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, family)),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 6),
+
+		/*     sk.type == SOCK_DGRAM)  { */
+		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, type)),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 4),
+
+		/*      user_ip4 = src4_rw_addr.sin_addr */
+		BPF_MOV32_IMM(BPF_REG_7, src4_rw_addr.sin_addr.s_addr),
+		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+			    offsetof(struct bpf_sock_addr, user_ip4)),
+
+		/*      user_port = src4_rw_addr.sin_port */
+		BPF_MOV32_IMM(BPF_REG_7, src4_rw_addr.sin_port),
+		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+			    offsetof(struct bpf_sock_addr, user_port)),
+		/* } */
+
+		/* return 1 */
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+
+	return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
+}
+
 static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test)
 {
 	return load_path(test, SENDMSG4_PROG_PATH);
@@ -901,6 +1043,39 @@ static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test)
 	return sendmsg6_rw_dst_asm_prog_load(test, SERV6_REWRITE_IP);
 }
 
+static int recvmsg6_rw_asm_prog_load(const struct sock_addr_test *test)
+{
+	struct sockaddr_in6 src6_rw_addr;
+
+	if (mk_sockaddr(AF_INET6, SERV6_IP, SERV6_PORT,
+			(struct sockaddr *)&src6_rw_addr,
+			sizeof(src6_rw_addr)) == -1)
+		return -1;
+
+	struct bpf_insn insns[] = {
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+		/* if (sk.family == AF_INET6) { */
+		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, family)),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 10),
+
+		STORE_IPV6(user_ip6, src6_rw_addr.sin6_addr.s6_addr32),
+
+		/*      user_port = dst6_rw_addr.sin6_port */
+		BPF_MOV32_IMM(BPF_REG_7, src6_rw_addr.sin6_port),
+		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+			    offsetof(struct bpf_sock_addr, user_port)),
+		/* } */
+
+		/* return 1 */
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+
+	return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
+}
+
 static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test)
 {
 	return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP);
@@ -1282,13 +1457,13 @@ out:
 	return err;
 }
 
-static int run_sendmsg_test_case(const struct sock_addr_test *test)
+static int run_xmsg_test_case(const struct sock_addr_test *test, int max_cmsg)
 {
 	socklen_t addr_len = sizeof(struct sockaddr_storage);
-	struct sockaddr_storage expected_src_addr;
-	struct sockaddr_storage requested_addr;
 	struct sockaddr_storage expected_addr;
-	struct sockaddr_storage real_src_addr;
+	struct sockaddr_storage server_addr;
+	struct sockaddr_storage sendmsg_addr;
+	struct sockaddr_storage recvmsg_addr;
 	int clientfd = -1;
 	int servfd = -1;
 	int set_cmsg;
@@ -1297,20 +1472,19 @@ static int run_sendmsg_test_case(const struct sock_addr_test *test)
 	if (test->type != SOCK_DGRAM)
 		goto err;
 
-	if (init_addrs(test, &requested_addr, &expected_addr,
-		       &expected_src_addr))
+	if (init_addrs(test, &sendmsg_addr, &server_addr, &expected_addr))
 		goto err;
 
 	/* Prepare server to sendmsg to */
-	servfd = start_server(test->type, &expected_addr, addr_len);
+	servfd = start_server(test->type, &server_addr, addr_len);
 	if (servfd == -1)
 		goto err;
 
-	for (set_cmsg = 0; set_cmsg <= 1; ++set_cmsg) {
+	for (set_cmsg = 0; set_cmsg <= max_cmsg; ++set_cmsg) {
 		if (clientfd >= 0)
 			close(clientfd);
 
-		clientfd = sendmsg_to_server(test->type, &requested_addr,
+		clientfd = sendmsg_to_server(test->type, &sendmsg_addr,
 					     addr_len, set_cmsg, /*flags*/0,
 					     &err);
 		if (err)
@@ -1330,10 +1504,10 @@ static int run_sendmsg_test_case(const struct sock_addr_test *test)
 		 * specific packet may differ from the one used by default and
 		 * returned by getsockname(2).
 		 */
-		if (recvmsg_from_client(servfd, &real_src_addr) == -1)
+		if (recvmsg_from_client(servfd, &recvmsg_addr) == -1)
 			goto err;
 
-		if (cmp_addr(&real_src_addr, &expected_src_addr, /*cmp_port*/0))
+		if (cmp_addr(&recvmsg_addr, &expected_addr, /*cmp_port*/0))
 			goto err;
 	}
 
@@ -1366,6 +1540,9 @@ static int run_test_case(int cgfd, const struct sock_addr_test *test)
 		goto out;
 	} else if (test->expected_result == ATTACH_REJECT || err) {
 		goto err;
+	} else if (test->expected_result == ATTACH_OKAY) {
+		err = 0;
+		goto out;
 	}
 
 	switch (test->attach_type) {
@@ -1379,7 +1556,11 @@ static int run_test_case(int cgfd, const struct sock_addr_test *test)
 		break;
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
-		err = run_sendmsg_test_case(test);
+		err = run_xmsg_test_case(test, 1);
+		break;
+	case BPF_CGROUP_UDP4_RECVMSG:
+	case BPF_CGROUP_UDP6_RECVMSG:
+		err = run_xmsg_test_case(test, 0);
 		break;
 	default:
 		goto err;